Unlock instant, AI-driven research and patent intelligence for your innovation.

Depth estimation device, depth estimation method, depth estimation program, image processing device, image processing method, and image processing program

A depth map, depth technology, applied in the field of image processing programs, can solve the problem of tedious inferring or adjusting the shape of the depth and so on

Active Publication Date: 2014-03-26
JVC KENWOOD CORP
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] However, it is cumbersome for the user to estimate or adjust the shape of the depth for each object.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Depth estimation device, depth estimation method, depth estimation program, image processing device, image processing method, and image processing program
  • Depth estimation device, depth estimation method, depth estimation program, image processing device, image processing method, and image processing program
  • Depth estimation device, depth estimation method, depth estimation program, image processing device, image processing method, and image processing program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 2

[0147] The depth map processing unit 20 according to Embodiment 2 individually adjusts the shape of the depth map generated by the depth map generating unit 10 for each of a plurality of target regions specified by a plurality of externally set masks. At this time, processing is performed using a volume relief pattern described later so that the central portion within the target area has a different depth value from the peripheral portion. Specifically, processing is performed so that the central portion within the target area has a depth value with a larger protrusion amount than the peripheral portion. It is more preferable to perform processing such that the protrusion amount of the central portion changes gradually from the peripheral portion to the central portion within the target area, compared with the peripheral portion. It is also preferable to perform processing such that the target area becomes a curved depth shape. It will be specifically described below.

[014...

Embodiment approach 3

[0193] By the method of Embodiment 2, the shape of the depth of the object in the image can be estimated easily and with high accuracy. However, in an actual image, the positions and shapes of the vertices and roots of the relief pattern determined by the method of Embodiment 2 may be different. Does not necessarily coincide with the most protruding position of the object. Next, according to Embodiment 3 described below, it is possible to estimate the depth shape of an object in an image with higher accuracy. Hereinafter, specific examples will be given and described for cases where it is more effective to use Embodiment 3. FIG.

[0194] Figure 21 (a)-(b) are figures which show the relief pattern of the person facing the front. Figure 21 (a) represents the original image, Figure 21 (b) represents a relief pattern. Figure 21 The dotted line in (b) is an auxiliary line showing the position of the target part in the original image. White indicates the bulge direction. i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a depth estimation device, a depth estimation method, a depth estimation program, an image processing device, an image processing method, and an image processing program. An outline identification unit identifies an outline of an object in a target image. A distance identification unit identifies the minimum distance between a target pixel in an object region and the outline. A depth value determination unit configured to determine a depth value of the target pixel in accordance with the distance. The distance identification unit can determine the minimum distance to the outline by spirally searching for a point of contact with the outline starting at the position of the target pixel.

Description

technical field [0001] The present invention relates to a depth estimation device, a depth estimation method, a depth estimation program, an image processing device, an image processing method, and an image processing program for estimating the depth of an object in an image. Background technique [0002] In recent years, 3D image contents (contents) such as 3D movies and 3D TV programs are gradually becoming popular. In order for the viewer to perform stereoscopic viewing, right-eye images and left-eye images with parallax are required. When displaying 3D video, the right-eye image and the left-eye image are time-divisionally displayed, and the right-eye image and the left-eye image are separated by image separation glasses such as shutter glasses or polarizing glasses. Accordingly, the viewer can view the right-eye image only with the right eye, and view the left-eye image only with the left eye, thereby performing stereoscopic viewing. Also, if the right-eye image and t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04N13/00H04N13/02
CPCG06T2207/10004G06T7/0051G06T15/08G06T7/50G06T2207/20104H04N13/261
Inventor 竹下浩
Owner JVC KENWOOD CORP